Python-AttributeError:';列表';对象没有属性
我正在尝试创建一个情绪分析程序。将要分析的推文从CSV文件中读取,分析后,将再次写入另一个CSV文件中。但是,我得到了AttributeError:'list'对象没有属性'lower'错误。错误似乎出现在代码的这一部分。CSV文件中的句子不允许执行此操作吗Python-AttributeError:';列表';对象没有属性,python,csv,Python,Csv,我正在尝试创建一个情绪分析程序。将要分析的推文从CSV文件中读取,分析后,将再次写入另一个CSV文件中。但是,我得到了AttributeError:'list'对象没有属性'lower'错误。错误似乎出现在代码的这一部分。CSV文件中的句子不允许执行此操作吗 def processTweet(tweet): # process the tweets #Convert to lower case tweet = tweet.lower()
def processTweet(tweet):
# process the tweets
#Convert to lower case
tweet = tweet.lower()
#Convert www.* or https?://* to URL
tweet = re.sub('((www\.[\s]+)|(https?://[^\s]+))','URL',tweet)
#Convert @username to AT_USER
tweet = re.sub('@[^\s]+','AT_USER',tweet)
#Remove additional white spaces
tweet = re.sub('[\s]+', ' ', tweet)
#Replace #word with word
tweet = re.sub(r'#([^\s]+)', r'\1', tweet)
#trim
tweet = tweet.strip('\'"')
return tweet
#end
#start getStopWordList
def getStopWordList(stopWordListFileName):
#read the stopwords
stopWords = []
stopWords.append('AT_USER')
stopWords.append('URL')
fp = open(stopWordListFileName, 'r')
line = fp.readline()
while line:
word = line.strip()
stopWords.append(word)
line = fp.readline()
fp.close()
return stopWords
#end
#start getfeatureVector
def getFeatureVector(tweet, stopWords):
featureVector = []
words = tweet.split()
for w in words:
#replace two or more with two occurrences
w = replaceTwoOrMore(w)
#strip punctuation
w = w.strip('\'"?,.')
#check if it consists of only words
val = re.search(r"^[a-zA-Z][a-zA-Z0-9]*[a-zA-Z]+[a-zA-Z0-9]*$", w)
#ignore if it is a stopWord
if(w in stopWords or val is None):
continue
else:
featureVector.append(w.lower())
return featureVector
#end
这是完整的代码
#import regex
import re
import csv
import pprint
import nltk.classify
#start replaceTwoOrMore
def replaceTwoOrMore(s):
#look for 2 or more repetitions of character
pattern = re.compile(r"(.)\1{1,}", re.DOTALL)
return pattern.sub(r"\1\1", s)
#end
#start process_tweet
def processTweet(tweet):
# process the tweets
#Convert to lower case
tweet = tweet.lower()
#Convert www.* or https?://* to URL
tweet = re.sub('((www\.[\s]+)|(https?://[^\s]+))','URL',tweet)
#Convert @username to AT_USER
tweet = re.sub('@[^\s]+','AT_USER',tweet)
#Remove additional white spaces
tweet = re.sub('[\s]+', ' ', tweet)
#Replace #word with word
tweet = re.sub(r'#([^\s]+)', r'\1', tweet)
#trim
tweet = tweet.strip('\'"')
return tweet
#end
#start getStopWordList
def getStopWordList(stopWordListFileName):
#read the stopwords
stopWords = []
stopWords.append('AT_USER')
stopWords.append('URL')
fp = open(stopWordListFileName, 'r')
line = fp.readline()
while line:
word = line.strip()
stopWords.append(word)
line = fp.readline()
fp.close()
return stopWords
#end
#start getfeatureVector
def getFeatureVector(tweet, stopWords):
featureVector = []
words = tweet.split()
for w in words:
#replace two or more with two occurrences
w = replaceTwoOrMore(w)
#strip punctuation
w = w.strip('\'"?,.')
#check if it consists of only words
val = re.search(r"^[a-zA-Z][a-zA-Z0-9]*[a-zA-Z]+[a-zA-Z0-9]*$", w)
#ignore if it is a stopWord
if(w in stopWords or val is None):
continue
else:
featureVector.append(w.lower())
return featureVector
#end
#start extract_features
def extract_features(tweet):
tweet_words = set(tweet)
features = {}
for word in featureList:
features['contains(%s)' % word] = (word in tweet_words)
return features
#end
#Read the tweets one by one and process it
inpTweets = csv.reader(open('data/sampleTweets.csv', 'rb'), delimiter=',', quotechar='"')
stopWords = getStopWordList('data/feature_list/stopwords.txt')
count = 0;
featureList = []
tweets = []
for row in inpTweets:
sentiment = row[0]
tweet = row[1]
processedTweet = processTweet(tweet)
featureVector = getFeatureVector(processedTweet, stopWords)
featureList.extend(featureVector)
tweets.append((featureVector, sentiment));
#end loop
# Remove featureList duplicates
featureList = list(set(featureList))
# Generate the training set
training_set = nltk.classify.util.apply_features(extract_features, tweets)
# Train the Naive Bayes classifier
NBClassifier = nltk.NaiveBayesClassifier.train(training_set)
# Test the classifier
# testTweet = 'RT @Jewelz2611 @mashable @apple, iphones r 2 expensive. Most went w/ htc/galaxy. No customer loyalty w/phone comp..'
with open('data/test_datasets.csv', 'r') as csvinput:
with open('data/test_datasets_output.csv', 'w') as csvoutput:
writer = csv.writer(csvoutput, lineterminator='\n')
reader = csv.reader(csvinput)
all=[]
row = next(reader)
for row in reader:
processedTestTweet = processTweet(row)
sentiment = NBClassifier.classify(extract_features(getFeatureVector(processedTestTweet, stopWords)))
row.append(sentiment)
all.append(row)
writer.writerows(all)
# print "testTweet = %s, sentiment = %s\n" % (testTweet, sentiment)
回溯和错误如下所示:
Traceback (most recent call last):
File "simpleDemo.py", line 114, in <module>
processedTestTweet = processTweet(row)
File "simpleDemo.py", line 19, in processTweet
tweet = tweet.lower()
AttributeError: 'list' object has no attribute 'lower'
回溯(最近一次呼叫最后一次):
文件“simpleDemo.py”,第114行,在
processedTestTweet=processTweet(行)
processTweet中第19行的文件“simpleDemo.py”
tweet=tweet.lower()
AttributeError:“list”对象没有属性“lower”
任何帮助都会非常感激。谢谢 您将
读取器
传递给processTweet()
而不是行
,但是processTweet()
需要一个字符串,您可能应该processTweet(行[1])
现在错误更改为AttributeError:'list'对象没有属性'lower'。我仍在努力解决问题。请显示完整的异常消息,包括堆栈跟踪信息。我在上面添加了完整的异常消息。请尝试在第114行中更改为processTweet(第[1]行),谢谢。我发现代码背后有逻辑错误,但现在已成功编译。